6 papers
ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning
Wenyang Hu, Junxiang Jia, Zhen Shu +3
Reinforcement Learning with Verifiable Rewards (RLVR) for language-model reasoning can fail at both extremes of task difficulty: easy prompts often produce all-correct, low-diversi…
Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading
Nicholas Sadjoli, Tim Siefken, Atin Ghosh +2
Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from the common industry practice…
Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis
Penny Chong, Harshavardhan Abichandani, Jiyuan Shen +4
Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a sca…
OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets
Jiyuan Shen, Peiyue Yuan, Atin Ghosh +2
Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In p…
Expanding the Action Space of LLMs to Reason Beyond Language
Zhongqi Yue, Weishi Wang, Yundaichuan Zhan +3
Large Language Models (LLMs) are powerful reasoners in natural language, but their actions are typically confined to outputting vocabulary tokens. As a result, interactions with ex…
Document Intelligence in the Era of Large Language Models: A Survey
Weishi Wang, Hengchang Hu, Zhijie Zhang +3
Document AI (DAI) has emerged as a vital application area, and is significantly transformed by the advent of large language models (LLMs). While earlier approaches relied on encode…